The avatar request will return information about the available voices in our text-to-speech API, such as speaker_ID, accent, avatar ID, and characteristics. The endpoint will assist your workflow in the following ways:

Voice Selection: Programmatically select the most suitable voice for your application based on criteria such as ID, accent, and speaking style.
Customization: Tailor the voice selection to match the specific needs or preferences of your users.
Flexibility: Easily experiment with different voices and styles, allowing for creative and innovative applications.
Efficiency: Quickly retrieve the latest information about available voices without the need for manual configuration, saving time and effort.

How do you use the endpoint?

Request

Make a GET request to this URL, including your API key in the header:

https://api.wellsaidlabs.com/v1/tts/avatars

An example curl command:

curl --location 'https://api.wellsaidlabs.com/v1/tts/avatars' \
--header 'X-API-KEY: <api-key-here>'

Response

Below is an example of a successful response showing one avatar with the following structure:

{
	"avatars": [
		{
			"name": "Alana B.",
			"id": 3,
			"style": "Narration",
			"gender": "female",
			"accent_type": "United States",
			"characteristics": [
				"Clear",
				"Crisp",
				"Focused",
				"Informative",
				"Strong"
			],
			"otherTags": [],
			"preview_audio": "https://media.graphassets.com/Ogq9S0cXRsOyUkYRjxWe",
			"locale": "en_US",
			"language": "English",
			"language_variant": "United States",
			"source": null
    }
  ]
}

Details of response

Field	type	notes
name	string	The name of the voice
id	integer	the ID is unique to the voice and voice style. For example, Wade C. conversational style is ID 46 and Wade C. narration style is ID 30
style	string	Available styles include: Narration, promo, conversational, character and custom NOTE: custom styles are used for our non-English language voices
gender	string	The gender of the avatar
accent_type	string	Indicates if there is a specific regional accent, such as United States — Appalachia
characteristics	array	Indicates subjective characteristics of the voice, such as crisp, informative, friendly, etc.
preview_audio	string	Returns a sample of the voice if the sample is available. If no sample is available, the result is null
locale	string	Shows a combination of language and the language variant, i.e. en_UK is English, United Kingdom
language	string	Indicates the language that the voice speaks
language_variant	string	Indicates the country where the language is spoken, i.e. United Kingdom for English or Mexico for Spanish.
source	string	This field should be null
otherTags	array	Other tags might include "new" or "featured"

📘
While not frequent, the details of an avatar may change, i.e. a new ID may be available for an avatar or a characteristic may change.